作者: Arjumand Younus , Colm O’Riordan , Gabriella Pasi
DOI: 10.1007/978-3-319-06028-6_83
关键词:
摘要: Personalized Web search offers a promising solution to the task of user-tailored information-seeking, and particularly in cases where same query may represent diverse information needs. A significant component any personalization model is means with which user's interests preferences build what termed as user profile. This work explores use Twitter microblog network source profile construction for personalization. We propose statistical language modeling approach taking into account various features network. The richness leads performance improvements retrieval accuracy. Furthermore, extended include similarity measure further improves engine performance.